A convolutional neural network segments yeast microscopy images with high accuracy

Dietler, Nicola; Minder, Matthias; Gligorovski, Vojislav; Economou, Augoustina Maria; Joly, Denis Alain Henri Lucien; Sadeghi, Ahmad Reza; Chan, Chun Hei Michael; Koziński, Mateusz; Weigert, Martin; Bitbol, Anne-Florence; Rahi, Sahand Jamal

doi:10.1038/s41467-020-19557-4

Cited by 94 publications

(116 citation statements)

References 32 publications

Supporting

Mentioning

116

Contrasting

Order By: Relevance

“…Nonetheless, this proof-of-concept implementation is more effective than pretrained or unsupervised methods for the Slimfield modality to date. To achieve a fully automated pipeline with true object labelling, we will incorporate additional postprocessing steps such as denoising, background subtraction, and removal of spurious cell boundaries (63).…”

Section: Supplementary Methodsmentioning

confidence: 99%

RecA and RecB: probing complexes of DNA repair proteins with mitomycin C in live Escherichia coli with single-molecule sensitivity

Payne-Dwyer

Syeda

Shepherd

et al. 2021

Preprint

View full text Add to dashboard Cite

The RecA protein and RecBCD complex are key bacterial components for the maintenance and repair of DNA, RecBCD a helicase-nuclease that uses homologous recombination to resolve double-stranded DNA breaks and also facilitating decoration of single-stranded DNA with RecA to form RecA filaments, a vital step in the double-stranded break DNA repair pathway. However, questions remain about the mechanistic roles of RecA and RecBCD in live cells. Here, we use millisecond super-resolved fluorescence microscopy to pinpoint the spatial localization of fluorescent reporters of RecA and the RecB at physiological levels of expression in individual live Escherichia coli cells. By introducing the DNA crosslinker mitomycin C, we induce DNA damage and quantify the resulting changes in stoichiometry, copy number and molecular mobilities of RecA and RecB. We find that both proteins accumulate in molecular hotspots to effect repair, resulting in RecA filamental stoichiometries equivalent to several hundred molecules that act largely in RecA tetramers before DNA damage, but switch to approximately hexameric subunits when mature filaments are formed. Unexpectedly, we find that the physiologically predominant form of RecB is a dimer.

show abstract

Section: Supplementary Methodsmentioning

confidence: 99%

RecA and RecB: probing complexes of DNA repair proteins with mitomycin C in live Escherichia coli with single-molecule sensitivity

Payne-Dwyer

Syeda

Shepherd

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Images were recorded on a Zeiss AxioImager M1, using Xcite Fire LED illumination (Excelitas), a Zeiss Plan-Apochromat 63x/1.40 Oil DIC objective and an ORCA-Flash4.0LT sCMOS camera (Hamamatsu) with Z sections spaced by 0.2 µm. Cells were segmented based on an in-focus brightfield image using YeaZ (Dietler et al, 2020).…”

Section: Quantification Of Gfp Signals In Single Cells (2d Segmentation and Projection)mentioning

confidence: 99%

Mitotic checkpoint gene expression is tuned by coding sequences

Esposito

et al. 2021

Preprint

View full text Add to dashboard Cite

The mitotic checkpoint (also called spindle assembly checkpoint, SAC) is a signaling pathway that safeguards proper chromosome segregation. Proper functioning of the SAC depends on adequate protein concentrations and appropriate stoichiometries between SAC proteins. Yet very little is known about SAC gene expression. Here, we show in fission yeast (S. pombe) that a combination of short mRNA half-lives and long protein half-lives supports stable SAC protein levels. For the SAC genes mad2+ and mad3+, their short mRNA half-lives depend on a high frequency of non-optimal codons and mRNA destabilization mediated through the RNA helicase Ste13 (S.c. Dhh1). In contrast, mad1+ mRNA half-life is short despite a relatively high frequency of optimal codons and despite the lack of known destabilizing motifs in its mRNA. Hence, although they are functionally related, different SAC genes employ different strategies of expression. Taken together, we propose that the codon usage of SAC genes is fine-tuned for proper SAC function. Our work shines light on the gene expression features that promote spindle assembly checkpoint function and suggests that synonymous mutations may weaken the checkpoint.

show abstract

“…In recent years, deep-learning based approaches have achieved notable success on nucleus segmentation tasks [3]- [21]. These works can be further categorized into two-stage and one-stage methods.…”

Section: Related Workmentioning

confidence: 99%

Boundary-Assisted Region Proposal Networks for Nucleus Segmentation

Chen

Ding

Tao

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Nucleus segmentation is a challenging task due to the crowded distribution and blurry boundaries of nuclei. Recent approaches represent nuclei by means of polygons to differentiate between touching and overlapping nuclei and have accordingly achieved promising performance. Each polygon is represented by a set of centroid-toboundary distances, which are in turn predicted by features of the centroid pixel for a single nucleus. However, using the centroid pixel alone does not provide sufficient contextual information for robust prediction. To handle this problem, we propose a Context-aware Polygon Proposal Network (CPP-Net) for nucleus segmentation. First, we sample a point set rather than one single pixel within each cell for distance prediction. This strategy substantially enhances contextual information and thereby improves the robustness of the prediction. Second, we propose a Confidencebased Weighting Module, which adaptively fuses the predictions from the sampled point set. Third, we introduce a novel Shape-Aware Perceptual (SAP) loss that constrains the shape of the predicted polygons. Here, the SAP loss is based on an additional network that is pre-trained by means of mapping the centroid probability map and the pixel-toboundary distance maps to a different nucleus representation. Extensive experiments justify the effectiveness of each component in the proposed CPP-Net. Finally, CPP-Net is found to achieve state-of-the-art performance on three publicly available databases, namely DSB2018, BBBC06, and PanNuke. Code of this paper will be released.

show abstract

A convolutional neural network segments yeast microscopy images with high accuracy

Cited by 94 publications

References 32 publications

RecA and RecB: probing complexes of DNA repair proteins with mitomycin C in live Escherichia coli with single-molecule sensitivity

RecA and RecB: probing complexes of DNA repair proteins with mitomycin C in live Escherichia coli with single-molecule sensitivity

Mitotic checkpoint gene expression is tuned by coding sequences

Boundary-Assisted Region Proposal Networks for Nucleus Segmentation

Contact Info

Product

Resources

About